Re: Performance under contention

Список
Период
Сортировка
От Tom Lane
Тема Re: Performance under contention
Дата
Msg-id 14229.1291818863@sss.pgh.pa.us
обсуждение исходный текст
Ответ на Re: Performance under contention  (Robert Haas)
Ответы Re: Performance under contention  (Robert Haas)
Список pgsql-performance
Дерево обсуждения
Performance under contention  (Ivan Voras, )
 Re: Performance under contention  ("Kevin Grittner", )
  Re: Performance under contention  (Ivan Voras, )
   Re: Performance under contention  (Jignesh Shah, )
    Re: Performance under contention  (Omar Kilani, )
   Re: Performance under contention  ("Kevin Grittner", )
    Re: Performance under contention  (Ivan Voras, )
     Re: Performance under contention  (Craig Ringer, )
      Re: Performance under contention  (Ivan Voras, )
      Re: Performance under contention  (Vitalii Tymchyshyn, )
       Re: Performance under contention  ("Kevin Grittner", )
 Re: Performance under contention  ("Kevin Grittner", )
  Re: Performance under contention  (Ivan Voras, )
 Re: Performance under contention  (Greg Smith, )
  Re: Performance under contention  (Ivan Voras, )
 Re: Performance under contention  (Robert Haas, )
  Re: Performance under contention  (Robert Haas, )
  Re: Performance under contention  (Jignesh Shah, )
   Re: Performance under contention  (Jignesh Shah, )
   Re: Performance under contention  (Robert Haas, )
    Re: Performance under contention  (Tom Lane, )
     Re: Performance under contention  (Dave Crooke, )
     Re: Performance under contention  (Robert Haas, )
    Re: Performance under contention  (Ivan Voras, )
     Re: Performance under contention  (Robert Haas, )
      Re: Performance under contention  (Ivan Voras, )
      Re: Performance under contention  (Віталій Тимчишин, )
       Re: Performance under contention  (Ivan Voras, )
       Re: Performance under contention  (Robert Haas, )
        Re: Performance under contention  (Robert Haas, )
         Re: Performance under contention  (Tom Lane, )
          Re: Performance under contention  (Robert Haas, )
           Re: Performance under contention  (Tom Lane, )
            Re: Performance under contention  (Robert Haas, ) 
Robert Haas <> writes:
>> Yeah, that was my concern, too, though Tom seems skeptical (perhaps
>> rightly). �And I'm not really sure why the PROCLOCKs need to be in a
>> hash table anyway - if we know the PROC and LOCK we can surely look up
>> the PROCLOCK pretty expensively by following the PROC SHM_QUEUE.

> Err, pretty INexpensively.

There are plenty of scenarios in which a proc might hold hundreds or
even thousands of locks.  pg_dump, for example.  You do not want to be
doing seq search there.

Now, it's possible that you could avoid *ever* needing to search for a
specific PROCLOCK, in which case eliminating the hash calculation
overhead might be worth it.  Of course, you'd still have to replicate
all the space-management functionality of a shared hash table.

            regards, tom lane

В списке pgsql-performance по дате отправления:

Предыдущее
От: Bryce Nesbitt
Дата:
Сообщение: Re: hashed subplan 5000x slower than two sequential operations
Следующее
От: Robert Haas
Дата:
Сообщение: Re: Performance under contention